Recommendation method based on article time popularity

Abstract

The invention discloses a recommendation method based on article time popularity. The method comprises the steps: S1, selecting a time interval delta t to divide a time axis of a data set into n segments, and defining the weight wi of an ith time zone; S2, carrying out the statistics of the distribution of articles in a time period through combining the proportion of the articles in the market; S3, accumulating the resource allocation of each time region to obtain a popularity score about the article alpha; S4, calculating a similarity matrix between the articles based on the CosRA similarityindex; S5, calculating to obtain a resource allocation result according to the similarity matrix in the step S4; and S6, adding a time factor, correcting the recommendation list of the target user i,and performing descending sort on the finally corrected recommendation list of the user i to obtain first L articles to generate a final recommendation list.

Description

technical field

[0001] The invention belongs to the technical field of item recommendation, and in particular relates to a recommendation method based on item time popularity. Background technique

[0002] The rapid development of the Internet age has changed our daily life and the way we obtain information. Information presents the characteristics of fast dissemination and huge amount of information. The overwhelming information has caused the problem of information overload when users obtain information. The problem of "information overload" means that people cannot quickly and accurately locate the information they need from the massive amount of information. A large amount of information reduces the efficiency of users to obtain information, causing the opposite effect of providing convenience to users. In order to solve these information overload problems, personalized recommendation systems came into being. The personalized recommendation system analyzes the simila...

Images